/azure-sre-agent

by Luke Murraylukemurraynz/hve-agent-skills1 stars

Design, configure, review, and operate production-grade Azure SRE Agent capabilities: response plans, scheduled tasks, HTTP triggers, custom agents, autonomous and review workflows, approval guardrails, AMBA observability, source RCA, connectors, MCP, governance hooks, WAF reviews, AI Foundry posture, Digital Native governance, postmortem generation, and KT discipline.

192 files
464.9 KB
Updated last month
GitHub
No alerts

Ask your Agent

Use this Skill: https://skilld.dev/gh/lukemurraynz/hve-agent-skills/azure-sre-agent

This session only. Nothing lands on disk.

referencesvalidation-and-release.md

2.4 KB raw

≈614 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Validation and Release Process

Use this process before sharing or publishing the skill package.

Local validation

Run the bundled validator from the skill root:

python scripts/validate-skill.py

The validator checks:

Agent Skills frontmatter shape, name rules, and description/compatibility length.
YAML and JSON parseability.
Template placeholder format and parameters.example.yaml coverage.
Bundle catalog completeness, dependency validity, resource references, manifest metadata, and catalog/manifest version parity.
Review-mode defaults for response plans, scheduled tasks, and HTTP triggers.
HTTP trigger disabled-by-default posture and bounded turn count.
Custom-agent allowed_skills coverage for Azure SRE Agent YAML.
Basic secret-pattern scanning for accidental committed tokens or keys.
Required hardening artifacts and local Markdown links.

Optional external validation

When available in the target environment, also run:

gh skill publish --dry-run

If skills-ref is installed, run:

skills-ref validate .

Treat external validation failures as release blockers. Treat external warnings as review items unless the target host clearly does not support the rule.

Release checklist

Before releasing a new zip:

Confirm SKILL.md still routes to bundles instead of embedding deep reference content.
Confirm every catalog bundle has matching version in its local bundle.yaml.
Confirm all production-impacting templates default to Review.
Confirm HTTP triggers default to isEnabled: false and use bounded maxTurns.
Confirm write-capable agents have approval, rollback, and validation wording.
Confirm connectors use placeholders only; never commit real tokens, API keys, bearer strings, client secrets, or storage keys.
Confirm source-map links still represent the current authoritative documentation.
Update CHANGELOG.md with added, changed, fixed, and validation notes.

Versioning guidance

Use semantic versioning for the package:

Patch: typo, example, or validator-only change that does not change behavior.
Minor: new bundle, new reference, new validator rule, or backward-compatible operating-model improvement.
Major: breaking package layout, bundle manifest schema change, or changed production safety posture.

Bundle versions may move independently, but catalog and bundle manifest versions must match.

Source: SKILL.md on GitHub

Third-party checks

No alerts8d3 checks · Risk SAFE

Gen Agent Trust Hub8d
The Azure SRE Agent skill provides a production-grade framework for managing Azure infrastructure using AI agents. It incorporates extensive safety documentation, approval-based hooks, and least-privilege role templates. The 'low' verdict is assigned due to the inherent risk of indirect prompt injection when the agent processes external incident data and source code, a necessary function for its SRE capabilities.
Socket8d
No alerts
Snyk8d
Risk: LOW · No issues

Provenance

Signed by skilld at 2cc2455. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated last month

Capability

compatibility: Azure SRE Agent; GitHub Copilot agent skills; new projects only

Other metadata

metadata: { "last_verified": "2026-08-25", "version": "2.23.3", "risk": "critical", "last_updated": "2026-08-25" }